Systap, LLC: Delivering Graphs at Scale

0
136

Systap delivers solutions that enable customers to scale their graphs. They have developed offerings to handle nearly all ranges of business challenges for graph and graph applications. This includes embedded graph database offerings, a high availability architecture for graphs up to 50B edges, a scale-out architecture for trillion-edge graphs, and GPU-accelerated solutions.

Systap’s Blazegraph is a ultra high-performance graph database supporting Blueprints and RDF/SPARQL APIs. It supports up to 50 Billion edges on a single machine and has a High Availability and Scale-out architecture. It is in production use for Fortune 500 customers such as EMC, Autodesk, and many others.

Systap’s GPU acceleration technology for graphs is a very unique offering in the market place. They have invented a way to exploit the main memory bandwidth advantages of GPUs to delivery graph analytics that is 100s of times faster than CPU-based approaches, up to 40X cheaper than existing super computer approaches, and 10,000X faster than disk-based approaches such as Hadoop. The company combined these solutions with their existing range of products to bring the power and speed of the GPU with the ease of use of existing platforms.

Systap is very excited about the next 3-5 years as the management has some good vision for the company in the next 3 years. “We see a tremendous amount of graph in graph applications and will be expanding our product offerings. We’re also building a patent portfolio around our key technologies.“

The company is getting the right mix of technology, business, and customers. One wants both be focused on building solutions, but also stay relevant and fresh with customer’s most difficult challenges.

Growth can be a challenge at times. It’s a welcome challenge, but you need to make sure that you are balancing keeping up with the hectic pace of growth while taking the time to invest in infrastructure to help you scale. Systap looks to focus on core areas and work closely with partners to leverage their expertise.

We are at a time when the software and hardware architectures are converging to make graphs at scale a reality. Advances in multi-core processing technology such as GPUs and others are helping to break through the barriers to Big Data for graphs. SYSTAP has launched Blazegraph GPU to provide drop-in GPU acceleration for its core Blazegraph product. “With Blazegraph GPU, you get 200-300X graph query acceleration just by switching to a GPU-enabled platform with almost zero changes to your application,” says Bebee.

In addition, SYSTAP’s Blazegraph’s DASL (“dazzle”) helps organizations process large graphs in near real. DASL can run on both one and multiple GPUs—a cluster of 64 NVIDIA K40 GPUs—to traverse a scale-free graph of more than four billion directed edges in mini-seconds. This helps in achieving a throughput of 32 billion traversed edges per second (32 GTEPS). Blazegraph DASL provides a Scala-based language to write graph analytics and in complementary to the Spark and Hadoop data ecosystems. Users of DASL typically see a 1000X increase in their graph analytics versus running directly in Spark with GPU acceleration.

Growth can be a challenge at times. It’s a welcome challenge, but you need to make sure that you are balancing keeping up with the hectic pace of growth while taking the time to invest in infrastructure to help you scale. We look to focus on core areas and work closely with partners to leverage their expertise.